GeoAI framework ranks urban basins to screen flood risk with human feedback
A Topology-Guided GeoAI Agentic Framework for Urban Flood Screening
Artificial Intelligence
Summary
Flooding in cities can be hard to predict because it depends on lots of natural and human factors. The authors created a computer system that uses maps and public data to find low-lying areas where water might collect, scoring them to show which are most at risk of flooding. The system uses a step-by-step logic and lets people check and adjust its choices to make sure results are clear and trustworthy. They tested it in Maryland and other places, finding good agreement with existing flood models while keeping humans in control.
What this means in practice
- •For urban planning teams: Identify potential flood-prone basins early to prioritize mitigation efforts using public geospatial data and human-adjustable analysis.
- •For emergency response coordinators: Generate transparent initial flood risk maps for rapid situational awareness during urban flooding events with user-controlled options.
Authors
Yutian Tao, Haoan Feng, Xin Xu, Leila De Floriani
Abstract
Open-world geographic artificial intelligence (GeoAI) agents can transform public geospatial data into accessible decision support for real-world challenges, but must balance autonomous reasoning with reliable spatial analysis and human oversight. We present a topology-guided GeoAI agentic framework for urban flood screening that takes a place name, drawn region, or uploaded boundary and returns ranked candidate basins with an interactive map and report. A deterministic controller retrieves public elevation, rainfall, soil, land-cover, exposure, and infrastructure layers, extracts terrain depressions with discrete Morse theory, and ranks basins with a relative flood-priority score. The language model acts only at recorded decision points: selecting a persistence threshold from a precomputed candidate table, drafting recommendations from computed evidence, and reviewing each recommendation against the same evidence. Three human-in-the-loop checkpoints let users revise the threshold, factor weights, or recommendation. In a College Park, Maryland case study, the selected threshold reduced 278 raw terrain minima to 70 basins, with 77% of these basins' lowest points also identified as sinks by a separately computed eight-direction (D8) flow-routing model. Across four further study areas, agreement ranged from 61% to 83%. By combining open data, explicit spatial reasoning, traceable evidence, and human oversight, the framework enables transparent first-pass flood screening while keeping consequential recommendations inspectable and user-controlled.